Earticle

최근 네트워크와 컴퓨터 기술의 발전으로 네트워크에 연결 가능한 PVR(Personal Video Recorder)은 인터넷을통해 데이터를 전송받아서 사용자가 원하는 시간에 원하는 비디오를 시청할 수 있게 해준다. 본 논문에서는 P2P PVR 시스템에서 라이브 시점을 시청하고 있는 PVR들이 자신의 유휴 저장 공간을 활용하여 라이브 시점 이전의 재생 구간 중에서 자신에게 할당된 구간의 데이터를 협력하여 캐싱함으로써 전체 재생 구간에서의 재생 연속성을 크게증가시키는 버퍼링 기법을 제안한다. 이 기법에서는 구간별 데이터의 실제 중복 정도와 사용자들의 시청 시점 분포를 동시에 고려하여 PVR들이 협력하여 데이터를 캐싱함으로써 평균 재생 연속성을 크게 증가시킨다.

With the advances in networking and computer technologies, networked PVRs enable users to watch the video they want when they want by receiving the data through the Internet. In this paper, we propose a buffering scheme to significantly increase the playback continuity in all the playback intervals prior to the live broadcasting time by caching the interval assigned to each PVR with its available buffer spaces. This scheme can increase the average playback continuity significantly by cooperating with other PVRs for caching the data, considering the degree of the data duplication in each playback interval and the distribution of users’ playback positions.

최근 영상 장비와 기술이 발전함에 따라 우리 군에서도 작전지역에 대한 정보를 획득하고, 효율적인 지휘통제에 활용하기 위해 수많은 영상정보가 생산되어 활용되고 있다. 이때 현재 군내에서 활용하고 있는 영상 재생장비는 저성능의 전술용 다기 능 단말기(TMFT)로부터 고성능의 영상서버에 이르기까지 매우 다양하고, 영상이 전송되는 네트워크 또한 저속의 전술정보통 신체계(TICN)로부터 초고속의 국방광대역통합망(M-BcN)에 이르기까지 다양하다. 따라서 이기종(異機種) 통신장비 및 네트 워크 환경에서 국방 영상정보를 효율적으로 전송할 수 있는 스트리밍 기법이 필요하다. 이 문제를 해결하기 위해 본 논문에서 는 확장비디오코딩(SVC) 및 균형선택 알고리즘 기반의 피투피(P2P) 스트리밍 기법을 제안한다. 비토렌트 기반의 시뮬레이터 를 활용한 성능분석결과 우리가 제안하는 균형선택 알고리즘 기반의 스트리밍 기법은 순차선택이나 희소선택 알고리즘에 비해 우수한 성능을 보였다.

Recently, with the rapid development of video equipment and technology, tremendous video information is produced and utilized in military domain to acquire battlefield information or for effective command control. Note that the video playback devices currently used in the military domain ranges from low-performance tactical multi-functional terminals (TMFT) to high-performance video servers and the networks where the video information is transmitted also range from the low speed tactical information and communication network (TICN) to ultra-high speed defense broadband converged networks such as M-BcN. Therefore, there is a need for an efficient streaming technique that can efficiently transmit defense video information in heterogeneous communication equipment and network environments. To solve the problem, this paper proposes a Scalable Video Coding (SVC) and balanced selection algorithm based Peer-to-Peer (P2P) streaming technique and the feasibility of the proposed technique is verified by simulations. The simulation results based on our BitTorrent simulator show that the proposed balanced selection scheme outperforms the sequential or rarest selection algorithm.

기존의 클라이언트/서버 구조 기반 클라우드 시스템에서의 높은 설치 및 유지비용 문제를 해결하기 위해 P2P 클라 우드 스토리지가 등장하게 되었다. 하지만 현재까지 P2P 클라우드 스토리지에 대한 연구는 주로 데이터 가용성을 보장하는 기술에 초점을 맞추었고 실시간 제약 조건이 있는 비디오의 안정적인 재생에 대한 연구는 거의 진행되지 않았다. 따라서 본 논문에서는 P2P 클라우드 스토리지에서 데이터 가용성뿐만 아니라 효율적인 비디오 전송을 지 원할 수 있도록 복제 기법과 erasure coding 기법의 장점을 동시에 활용하는 하이브리드 데이터 중복 기법을 제안 한다.

To solve the problems caused by such high installation and maintenance cost in the conventional cloud 1)systems based on client/server architectures, P2P cloud storages have been emerged. However, recent research on P2P cloud storages has focused on the technology to guarantee data availability but there have been little research on supporting stable playback of video data with real-time constraints. In this paper, we therefore propose a hybrid data redundancy scheme that takes advantages of both replication and erasure coding simultaneously to support efficient video transmission as well as data availability in P2P cloud storages.

타임시프트 기능을 지원하는 P2P 라이브 스트리밍 시스템에서는 피어가 원하는 재생 시점으로 이동 연산을 요청하 더라도 이동 시점에서 재생 중인 모든 피어들이 연결 가능한 이웃 피어 수가 이미 최대인 경우에는 원하는 시점에서 데이터를 전송받을 수 없다. 따라서 본 논문에서는 원하는 재생 시점에 있는 기존의 피어 간의 연결을 해제하고 새로 운 피어와 연결함으로써 원하는 시점과 최대한 가까운 시점으로 이동할 수 있게 하는 이웃 피어 선정 기법을 제안한 다. 시뮬레이션 실험을 통해 본 논문에서 제안한 연결 교체를 통한 이웃 피어 선정 기법이 기존의 메시 기반 P2P 시 스템의 이웃 피어 선정 기법에 비해 이동의 정확성이 높고 이동 연산 후 재생 지연 시간도 낮아진다는 것을 보인다.

Even though a peer requests to jump to a desired playback position in P2P live streaming systems supporting time-shift functions, it cannot receive data at the desired position if all the peers that are playing back around the position already have the maximum number of neighbor peers to be connected. In this paper, we therefore propose a neighbor peer selection scheme to make the requesting peer jump to the position as close to the desired one as possible by releasing an existing connection of peers at the desired position and connect them to the requesting peer. By simulation experiments, we show that our neighbor peer selection scheme through connection replacement performs better than the conventional neighbor peer selection scheme in terms of the accuracy of jumping position and initial playback delay.

Peer-to-Peer (P2P) streaming is being considered as the most promising approach to deliver real-time video to large scale users over the Internet. Neighbor selection is one of the key components to construct overlay topology for P2P streaming systems. Currently the majority of QoS-aware neighbor selection approaches assume that the allocated bandwidth resources to individual peers are proportional to their incoming bandwidth rather than their outgoing bandwidth and don’t suit for bandwidth resource scarce environments. In this paper, we incorporate taxation-based incentive mechanism into QoS aware neighbor selection method to computer the allocated number of neighbors of peers. The main contribution of this paper is: i) we incorporate linear taxation-model into SVC-based layered media delivery to determined the connection number of peers and propose a distributed bandwidth resource allocation policy; ii) when selecting neighbors, it considers existing peers’ uplink capacity and source to peer’s delay as a whole to handle long cumulate delay caused by bandwidth aggregation in mesh-based system. Simulation results demonstrate that under resource constraint scene, our proposed method can receive good performance compared with fixed random neighbor selection method and QoS-aware method based on bandwidth-latency ratio on the metric of the chunk loss rate, the average delivery delay, control overhead and PSNR.

The traditional Gossip protocol selects the neighbor nodes randomly. It does not consider the factors, such as the capacities of network transmission and node storage, which affect the network performance. It further causes the drawback of successful search ratio relatively lower, and also network transmission payloads have the characteristics of randomness. In this paper, to overcome those drawbacks of traditional Gossip protocol, a neighbor node selection algorithm has been studied, and various factors that may affect the neighbor node selection have been analyzed in P2P networks. A new neighbor node selection policy has been proposed, which is a reliable Gossip message transmission Protocol based on fuzzy theory. Empirical simulation experiments with various data analysis have demonstrated the improvement of efficiency of the proposed strategy on node selection and correctness of the proposed algorithm in P2P networks.

The combination of social network and P2P streaming service created a new kind of peers, these peers only share their bandwidth to social-connected peers and they do not need to watch the streaming video. Because of the particularity of such peers, ordinary P2P modelsdo not apply to this type of peers. Therefore, we propose a social network-based bandwidth sharing model. By creating download and upload neighbor list, our model separates the transmission of data blocks. Peer requests data blocks from peers in download neighbor list by the data block missing degree of peers in upload neighbor list. Meanwhile we redefine the buffer of social-connected peers, make the social-connected peers better collaborate with the sharing peers. Therefore the social-connected peers will not receive duplicate data blocks. Experiment data shows our sharing model could maximize the sharing ratio of sharing peers, and improve the playback quality of social-connected peers. When the number of sharing peers reaches a certain proportion, the playback delay of P2P streaming service with sharing peers is better than the playback delay of normal P2P streaming service.

The P2P multicast that has been recently presented as an alternative to the client-server architectures has been getting much persuasion by the system resource and the network bandwidth and the advancement of the network cost. Also, studies on P2P networks for the effective services of VOD streams in the mobile environment have been actively carried out. They however, have failed to consider fully characteristics proper to mobile nodes, such as the constraints of available resources and the variability of service time and location, since their concepts have merely expanded the characteristics of the existing P2P wired networks to mobile nodes. We suggested a scheme for the effective VOD streaming service on the mobile node oriented P2P network. Specifically, our scheme prevents the overconsumption of resources for a parent node when it uploads streams for other node, and enables a child node to keep downloading streams effectively even after its parent node exits the network. Our simulation showed the favorable performance of our system compared to the existing systems, in terms of resource utilization for nodes joining the P2P service and the utilization of shared cache.

Chunk scheduling is one of the key components in P2P streaming systems. Most of previous research works focus on receiver side’s chunk/peer selection strategies and neglect the service order and available uplink bandwidth allocation problem at supplier side, which will cause the user’s video quality descending under overloaded operating environments. In this paper, we propose the supplier side chunk priority model, formulate the supplier side scheduling problem as a linear programming problem and derive a greedy bandwidth resource allocation algorithm to solve it. The simulations demonstrate the proposed scheme effective comparing to the FCFS (First Come First Service) scheme.

Streaming media technology has seen tremendous growth and is currently a popular research area. While most of the work on streaming media technology is on ensuring the quality of the video playback and the scalability of the overall media streaming solution, there are few researches that are being conducted to address the limitations of the network, computer hardware nor the streaming media characteristics. These are the other factors that causes network capacity bottleneck. It is generally accepted that a Peer-to-Peer network is suitable for streaming media network and these can be classified into two main network architectures; a tree- based architecture and a mesh-based architecture. In this paper, we investigate and evaluate the network limitations between a Peer-to-Peer tree-based architecture and the more popular mesh-based architecture for media streaming performance. The simulations were conducted under various real-world scenarios and evaluated using different critical performance metrics that affects the reliability of the streaming quality and performance.

본 논문에서는 P2P 라이브 스트리밍 시스템에서 각 피어의 캐싱과 프리페칭 영역 비율을 조절하여 성능을 향상시키는 버퍼링 기법을 제안한다. 이를 위해 재생 시점을 기준으로 피어들을 그룹핑한 후 그룹 내 각 피어의 상대 적인 재생 시점에 따라 캐싱과 프리페칭을 적응적으로 결정한다. 즉, 피어의 재생 시점이 최근일수록 캐싱 영역의 비 율을 증가시키고 이른 시점일수록 프리페칭 영역을 증가시킴으로써 그룹 내 피어들 간에 버퍼맵 구간의 중복 정도를 크게 높일 수 있다. 마지막으로 시뮬레이션 실험을 통해 본 논문에서 제안하는 프리페칭/캐싱 통합 버퍼링 기법이 기 존 고정 영역 버퍼링 기법보다 평균 지터 비율, 초기 재생 지연 시간 및 공유 가능한 버퍼맵 비율 등에서 우수한 성 능을 나타낸다는 것을 보인다.

In this paper, we propose a buffering scheme to improve the performance in P2P live streaming systems by adjusting the ratio of caching and prefetching portion of each peer. To this end, we assign all the peers into many groups depending on their playback periods. We then determine the ratio of caching and prefetching portion in each peer depending on its playback time position relative to those of other peers within the same group. In other words, as the playback position of a peer gets later, we increase the ratio of its caching portion. On the contrary, as the playback position of a peer gets eariler, we increase the ratio of its prefetching portion. This can significantly increase the degree of data duplication among peers that belong to each specific group. By simulation experiments, we show that our proposed an integrated prefetching/caching scheme can improve the performance considerably in terms of jitter ratio, initial playback delay and shared buffermap ratio when compared to the existing fixed portion buffering scheme.

Peer-to-Peer content delivery technology recently begins to be used not only for file sharing applications such as eDonkey but also for every kind of content services. KBS, a broadcasting company in Korea, is aggressively driving to apply Peer-to-Peer technology to KBS's commercial internet video service but we found that there are two big huddles. First, end users may refuse to share their own resources for KBS's cost reduction using Peer-to-Peer content delivery technology. Second, it may cause that the number of free-riders increases and the efficiency of the overall system would fall. From commercial service provider's perspective, we have to avoid that end users have unfavorable impressions on the service and the usefulness of Peer-to-Peer technology decreases. In order to overcome these problems, we studied how to offer incentive to end users and how much incentive would be reasonable, and then applied the result to real service for verification.

Recent studies have convinced that network coding can improve the performance of live media streaming in terms of startup delay, resilience to peer dynamics, as well as reduced bandwidth cost on dedicated streaming servers. However, there still exist some strategy drawbacks and neglected problems which need to be further researched. In addition to the commonly used evaluation parameters of the network and user experiences mentioned above, we focus on additional key factors, playback lag and switch lag, which have not been fully explored in previous work. In this paper, we present SonicStream, a novel and fully implemented live peer to peer (P2P) media streaming system with consideration of rich user experiences, including startup delay, playback continuity, playback lag, switch lag, etc. In pursuit of a further enhanced user experience, we revise traditional peer selection/data scheduling methods. Through a series of experimental evaluations and a cautious comparison with the latest similar work $R^2$, the superior performance of SonicStream has been preliminarily verified.

오늘날, P2P(Peer-to-Peer) 서비스는 기존의 파일 공유를 위해 제한적으로 이용되었던 것과 비교할 때, 현저한 서비스 발전으로 거듭나고 있다. 특히 P2P에서 미디어 스트리밍 서비스는 이용자에게 매력적인 서비스로써 서비스 품질에 대한 만족도를 높이기 위한 많은 기술 들이 제안되었다. 그러나 서비스 환경이 유선에서 모바일로 전환되어감에 따라, 제한적인 배터리 용량은 해결되어야 할 또 다른 중요한 문제로 이슈화되고 있다. 따라서 모바일 환경에서 안정적인 P2P 미디어 스트리밍 서비스를 제공하기 위해서는 기존 방식에 문제가 된, 에너지 이슈를 함께 고려야 해야 할 것이다. 본 논문에서는 모바일 단말의 에너지를 고려한 피어 선택 방법으로 에너지를 고려한 자원입찰 메커니즘인 RBM-CU(Resource Bidding Mechanism with Combined Utility Function) 정의하고, 에너지를 고려한 최적 대역폭 할당 방법을 제시한다. 그리고 제안한 방법을 적용하기 위해 시스템을 모델링 하고, 특성을 분석하기 위해 RBM-CU의 대역폭 할당 방법을 제시하고 분석한다. 그 결과, 본 논문에서 제시한 RBM-CU를 이용한 에너지 기반 피어 선택 방법이 모바일 환경에서 유효하고 타당성 있음을 확인하였다.

P2P techniques have been considered as a promising solution for improving media streaming services. While the early usage of P2P was limited, recently it is being used in various fields. Several technologies have been proposed to improve the satisfaction of the quality of service, especially for the P2P media streaming service which is quite attractive to users. However, according to the switching of wired to mobile environments, another important issue of P2P is that of limited battery capacity which needs to be solved. Therefore, to provide a reliable P2P media streaming service in mobile environments, the existing problems regarding the energy constraint issues should be considered. In this paper, the energy aware resource bidding mechanism, RBM-CU (Resource Bidding Mechanism with Combined Utility Function), while considering the energy aware peer selection scheme in a mobile terminal, is introduced for allocating the optimal bandwidth to competing nodes. We present the system model to apply RBM-CU. Through the analysis of characteristic the RBM-CU mechanism, we also represent the optimal resource distribution mechanism between the source node and competing nodes. As a result, we confirm that the proposed RBM-CU scheme is useful and adaptive to the mobile P2P media streaming service.

P2P 분산 모바일 네트워크 환경에서 스트리밍 미디어 서비스의 QoS는 혼잡, 지연, 간섭 등과 같은 오버헤드에 많은 영향을 받는다. 미디어 객체의 중요도는 시간에 따라 변하기 때문이다. 본 논문에서는 이러한 문제를 해결하기 위하여 새로운 퍼지 유사도 기반의 멀티-레벨 스트리밍 기법 FSMS+를 제안하며, 제안된 기법은 오버헤드로 인하여 발생되는 스트리밍 서비스의 성능 저하를 최소화한다. 이를 위해서 퍼지 유사도 기반의 적합도 기법을 적용하며, 이것은 오버헤드가 최소인 스트리밍 미디어 객체를 동적으로 스트림할 수 있게 한다. 시뮬레이션 결과 제안된 기법은 거리 기반 기법, 디스크 캐싱 기법, 그리고 프리픽스 기법과 비교할 때 재전송율, 혼잡 제어율, 그리고 지연율의 성능이 보다 우수함을 보인다.

In P2P distribution mobile networks, QoS of streaming media services are under heavy influence from overheads such as congestion, latency, and interference. The problem is further complicated by the fact that the popularity of media objects changes over time. This paper proposes a new FSMS+ (Fuzzy Similarity-based Multi-level Streaming Scheme) which minimizes performance degradation of streaming services due to overhead. We then utilize fuzzy similarity-based relevance that can dynamically stream the streaming media object with minimum overhead. The simulation result showed that the proposed scheme has better performance in retransmission rate, congestion control rate and latency rate than the other existing methods of distance method, DC (disk caching) method, and prefix method.

본 논문에서는 Hybrid CDN/P2P 구조를 기반으로 최적화된 미디어 데이터 탐색과 전송을 수행하며 사용자의 요청 가능성 예측을 통한 선별적 저장을 통해 사용자로의 끊김없는 데이터 전송과 불필요한 트래픽의 감소를 가능하게 한다. 또한 전송지연 및 패킷 손실의 가능성을 최소화하여 실시간으로 미디어를 활용할 수 있도록 하는 새로운 미디어 관리 기법을 제안한다. 이를 위해 각 미디어를 논리적인 세그먼트로 나누어 구성하고 각 세그먼트에 대한 가중치를 지속적으로 계산하며 계산된 가중치에 따라 세그먼트 데이터의 저장 여부를 결정하도록 한다. 또한 네트워크상에 산재되어 있는 컴퓨팅 노드들을 거리에 따라 지역적 그룹으로 지정하고 해당 그룹 내에서 저장 공간을 효율적으로 공유하고 활용하도록 한다. 제안하는 기법의 효율성을 검증하기 위해 수행된 실험을 통해 제안하는 방식이 기존의 방법들에 비해 비교적 좋은 성능 평가가 도출되는 것을 확인하였으며 이는 전송과정에서 발생되는 초기 지연시간 감소와 끊김 없는 전송 모두를 가능하게 할 수 있음을 알 수 있다.

In this paper, optimized media data retrieval and transmission based on the Hybrid CDN/P2P architecture and selective storage through user's prediction of requestability enable seamless data transfer to users and reduction of unnecessary traffic. We also propose a new media management method to minimize the possibility of transmission delay and packet loss so that media can be utilized in real time. To this end, we construct each media into logical segments, continuously compute weights for each segment, and determine whether to store segment data based on the calculated weights. We also designate scattered computing nodes on the network as local groups by distance and ensure that storage space is efficiently shared and utilized within those groups. Experiments conducted to verify the efficiency of the proposed technique have shown that the proposed method yields a relatively good performance evaluation compared to the existing methods, which can enable both initial latency reduction and seamless transmission.

In this paper, we propose an optimal streaming service method based on Hybrid CDN/P2P architecture. Recently, video streaming utilizes a CDN (Content Delivery Network) operation technique based on a Proxy Server, which is an end node located close to a user. However, since CDN has a fixed network traffic bandwidth and data information exchange among CDNs in the network is not smooth, it is difficult to guarantee traffic congestion and quality of image service. In the hybrid CDN/P2P network, a data selection technique is used to select only the data that is expected to be continuously requested among all the data in order to guarantee the QoS of the user who utilizes the limited bandwidth efficiently. In order to search user requested data, this technique effectively retrieves the storage information of the constituent nodes of CDN and P2P, and stores the new image information and calculates the deletion priority based on the request possibility as needed. Therefore, the streaming service scheme proposed in this paper can effectively improve the quality of the video streaming service on the network.

본 논문에서는 새로운 미디어 관리 및 전송 운용에 적합한 네트워크 형태인 Hybrid CDN/P2P 아키텍처 기반 하에서 전송 지연과 패킷 손실을 최소화하는 동시에 안정적인 망 운용 정책을 제안한다. 또한 실시간으로 대용량, 고품질의 미디어를 효과적으로 전송하고 네트워크 품질을 향상시킬 수 있도록 하기 위해 전송 스케줄링과 사용자의 요구 패턴을 기반으로 한 끊김 없는 데이터 전송 그리고 이를 통한 트래픽 및 로드를 관리하는 방법을 함께 제안한다. 제안하는 영상 전송기법의 효율성 및 적용 적합도를 검증하기 위해 수행된 실험결과에 따라 제안하는 방법이 기존에 제안된 방법에 비해 비교적 좋은 성능 평가가 이루어졌음을 확인하였다. 이는 프록시 서버 간의 협력적 운용 방법을 통해 보유 데이터 정보를 상호 공유하고 이를 통해 각 노드가 원하는 데이터를 전송받도록 하는 동시에 실행 버퍼 전송 기법을 통해 데이터 전송 과정에서 전달된 데이터의 재사용성을 높이고 있기 때문이다.

Recently, hybrid CDN/P2P video streaming architecture is specially designed and deployed to achieve the scalability of P2P networks and the desired low delay and high throughput of CDNs. In this paper, we propose a cooperative video streaming and active node buffer management technique in hybrid CDN/P2P architecture. The key idea of this streaming strategy is to minimize network latency such as jitter and packet loss and to maximize the QoS(quality of service) by effectively and efficiently utilizing the information sharing of file location in CDN's proxy server which is an end node located close to a user and P2P network. Through simulation, we show that the proposed cooperative video streaming and active node buffer management technique based on CDN and P2P network improves the performance of realtime video streaming compared to previous methods.

Peer-to-Peer (P2P) streaming is a method for sharing data on the network without the support of server. One of the main challenge is to provide a high quality of service through the dynamic behavior of the network because a user may join or leave anytime. We realized that the streaming users- who use mobile devices with 3G/4G connection, may stop watching live video after a while if they find the video is out of their interest. Users leaving causes dynamic and affect the data delivery. On the other hand, the storage users-who use PC with wired Internet, are downloading the video do not have the concern of interest and playback quality, until they start to watch the video. Hence, the storage users are relatively more stable than streaming users. This paper, we propose an efficient architecture by organizing storage users position are closer to the broadcaster than streaming users position. And then, we apply our idea on hybrid model that combines the benefits of tree-based and mesh-based models to decrease startup delay, packet lost and control overhead compare with other systems.